한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

  • 제29권11호
  • /
  • Pages.153-161
  • /
  • 2024
  • /
  • 1598-849X(pISSN)
  • /
  • 2383-9945(eISSN)
한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

Research on Channel-Wise Preprocessing for Enhanced Infrared Object Detection

  • Jae-Uk Kim (Intelligence Software Team, Hanwha-Systems Co., Ltd.) ;
  • Byung-In Choi (Intelligence Software Team, Hanwha-Systems Co., Ltd.)
  • 투고 : 2024.10.17
  • 심사 : 2024.11.20
  • 발행 : 2024.11.29
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 단일 채널(Channel)로 구성된 적외선(Infrared, IR) 영상이 RGB 기반 탐지 모델에 직접 적용하기 어렵다는 한계를 해결하고자 하였다. 기존에는 단일 채널을 단순히 3채널로 복제하는 방식이 주로 사용되었으나, 이 방법은 정보 중복으로 인해 탐지 성능이 제한될 가능성이 있었다. 본 연구는 이러한 한계를 극복하기 위해 적외선 영상의 단일 채널을 3채널로 복제한 뒤, 각 채널에 CLAHE(Contrast Limited Adaptive Histogram Equalization), 라플라스 필터(Laplacian Filter), Top-hat 변환의 전처리 기법을 적용하여 탐지 성능을 높이는 방법을 제안한다. 본 연구에서는 RT-DETRv2 탐지 모델과 Anti-UAV300 데이터 세트(Dataset)를 사용해 10프레임(Frame) 간격으로 샘플링(Sampling)한 적외선 영상을 실험에 활용하였다. 이를 통해 각 전처리 기법의 효과를 평가하고 최적 구성을 도출한 결과, mAP(mean Average Precision) 성능이 기존 방식 대비 2.2% 향상되었다. 이는 단순 복제 방식보다 성능이 개선됨을 확인한 것으로, 본 연구는 적외선 영상 기반 객체 탐지 성능 개선을 위한 새로운 접근법을 제시하며, 향후 적외선 카메라가 사용되는 재난 상황, 야간 감시 정찰, 자율주행 차량의 저조도 환경에서의 객체 검출 분야에서 기여할 가능성이 클 것으로 기대된다.

In this paper, we address the limitation of single-channel infrared (IR) images, which are difficult to directly apply to RGB-based detection models. Previously, a single channel was often replicated into three channels; however, this approach may limit detection performance due to information redundancy. To overcome this limitation, we propose a method that replicates the single-channel IR image into three channels, with each channel processed using different preprocessing techniques, such as CLAHE (Contrast Limited Adaptive Histogram Equalization), Laplacian Filter, and Top-hat transform, to improve detection performance. In this study, we utilized the RT-DETRv2 detection model and the Anti-UAV300 dataset, using IR images sampled at 10-frame intervals for our experiments. By evaluating the effects of each preprocessing technique and deriving the optimal configuration, our method achieved a 2.2% improvement in mean Average Precision (mAP) over conventional methods. This confirms that our method enhances performance over simple replication, presenting a novel approach to improving object detection performance in IR imaging, with promising applications across various fields, particularly in disaster situations where infrared cameras are utilized, as well as in nighttime surveillance and reconnaissance.

키워드

참고문헌

  1. A. Akula, Ripul Ghosh, and H. K. Sardana, "Thermal imaging and its application in defence systems," American Institute of Physics, Vol. 1391. No. 1, October 2011. DOI: 10.1063/1.3643540 
  2. R. S. Allison, J. M. Johnston, G. Craig, and S. Jennings, "Airborne optical and thermal remote sensing for wildfire detection and monitoring." Sensors, 16(8), 2016. DOI: 10.3390/s16081226. 
  3. M. Bertozzi, A. Broggi, and A. Fascioli, "Pedestrian Detection in Far Infrared Images based on the use of Probabilistic Templates," Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 134-139, Istanbul, Turkey, July 2007. DOI: 10.1109/IVS.2007.4290135. 
  4. Baek, Jae-Yong, et al., "Research on Local and Global Infrared Image Pre-Processing Methods for Deep Learning Based Guided Weapon Target Detection," Journal of The Korea Society of Computer and Information Vol. 29. No. 7, pp.41-51, April 2024. DOI: 10.9708/jksci.2024.29.07.041 
  5. Myung-Won Shin, "A Study on the Development of High Energy Laser(HEL) Weapon System," Journal of the Korea Academia-Industrial cooperation Society, Vol. 23, No. 5, pp.141-150, May 2024. DOI: 10.5762/KAIS.2022.23.5.141 
  6. Seung-Hyun Kang, "The Development Trend and Future Direction of Laser-Based Individual Combat Firearm Weapon Systems," Journal of the Korea Academia-Industrial cooperation Society, Vol. 25, No. 6, pp.544-552, July 2024. DOI: 10.5762/KAIS.2024.25.6.544 
  7. S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. ter Haar Romeny, J. B. Zimmerman, and K. Zuiderveld, "Adaptive histogram equalization and its variations," Computer vision, graphics, and image processing Vol. 39, No. 3, pp.355-368, September 1987. DOI : 10.1016/S0734-189X(87)80186-X 
  8. K. Zuiderveld, "Contrast Limited Adaptive Histogram Equalization," In Graphics Gems IV, Academic Press Professional, Inc., pp. 474-485, August 1994. DOI: 10.5555/180895.180940 
  9. J. Serra, "Image Analysis and Mathematical Morphology," Academic Press, January 1983. DOI: 10.1002/cyto.990040213 
  10. P. A. Mlsna, J. J. Rodriguez, "Gradient and Laplacian Edge Detection," In The Essential Guide to Image Processing, Academic Press, pp. 495-524, April 2009. DOI: 10.1016/B978-0-12-374457-9.00019-6 
  11. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, Las Vegas, USA, June 2016. DOI: 10.1109/CVPR.2016.91 
  12. A. Bochkovskiy, C.-Y. Wang, and H-Y. M. Liao, "Yolov4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, April 2020. DOI: 10.48550/arXiv.2004.10934 
  13. N. Carion, et al. "End-to-end Object Detection with Transformers," In European Conference on Computer Vision, pp. 213-229, Cham, Switzerland, August 2020. DOI: 10.48550/arXiv.2005.12872 
  14. Y. Zhao, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov and S. Zagoruyko, "DETRs Beat Yolos on Real-Time Object Detection," In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1234-1245, 2024. DOI: 10.1109/CVPR46437.2024.00132 
  15. W. Lv, Y. Zhao, Q. Chang, K. Huang, G. Wang, and Y. Liu, "RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer," arXiv preprint arXiv:2407. 17140, 2024. URL: https://arxiv.org/abs/2407.17140 
  16. Y. Yang, Z. Jiang, B. Yang, and X. Xia, "YOLO-IR-Free: An Improved Algorithm for Real-Time Detection of Vehicles in Infrared Images." Sensors Vol. 23, No. 21, August 2023. DOI: 10.3390/s23218723 
  17. Z. Yuan, J. Zeng, Z. Wei, L. Jin, S. Zhao, X. Liu, Y. Zhang, G. Zhow, "CLAHE-based low-light image enhancement for robust object detection in overhead power transmission system,", IEEE Transactions on Power Delivery, Vol. 38, pp. 2240-2243, April 2023. DOI: 10.1109/TPWRD.2023.3269206 
  18. P. Zhu, L. Wen, D. Du, X. Bian, H. Ling, Q. Hu, B. Cheng, C. Sun, Y. Lei, W. Hu, and L. Jiao, "Anti-UAV: A Large-Scale Benchmark for Vision-Based UAV Tracking," IEEE Transactions on Multimedia, Vol. 25, No. 2, pp. 486-500, April 2021. DOI: 10.1109/TMM.2021.3073459 
  19. J. Zhao, J. Li, L. Jin, J. Chu, Z. Zhang, J. Wang, J. Xia, K. Wang, Y. Liu, and Gulshad, Anti-Unmanned Aerial Vehicle (UAV), https://github.com/ZhaoJ9014/Anti-UAV 
  20. T. Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, J. Hays, P. Perona, D. Ramanan, C. L. Zitnic and P. Dollar, "Microsoft COCO: Common Objects in Context," In Proceedings of the European Conference on Computer Vision (ECCV), pp. 740-755, Zurich, Switzerland, September 2014. DOI: 10.1007/978-3-319-10602-1_48